使用GPT和图像通过Telegram机器人界面生成病毒式LinkedIn内容
中级
这是一个Content Creation, Multimodal AI领域的自动化工作流，包含 15 个节点。主要使用 SplitOut, Telegram, HttpRequest, Agent, TelegramTrigger 等节点。 使用GPT和图像通过Telegram机器人界面生成病毒式LinkedIn内容
前置要求
- •Telegram Bot Token
- •可能需要目标 API 的认证凭证
- •OpenAI API Key
使用的节点 (15)
工作流预览
可视化展示节点连接关系，支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"meta": {
"instanceId": "744512f77fc51097e8ca6be7a65f53ac98b545404aa0360c7832162d51cb4e02"
},
"nodes": [
{
"id": "e3517ee8-ff96-4a9c-8000-789edfde137f",
"name": "Telegram 触发器",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-816,
112
],
"webhookId": "e02b3b11-f6e1-4f34-9b8c-c5c14c1a5461",
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "AarnxB8wJEK5UvZA",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "3493a02f-74b5-4f47-a65c-d29270527f2d",
"name": "拆分输出",
"type": "n8n-nodes-base.splitOut",
"position": [
48,
-48
],
"parameters": {
"options": {},
"fieldToSplitOut": "result.data.results"
},
"typeVersion": 1
},
{
"id": "56bf0f72-13b6-4dbb-9076-21d2dcaf2147",
"name": "生成图片",
"type": "n8n-nodes-base.httpRequest",
"position": [
-192,
-48
],
"parameters": {
"url": "https://ai-text-to-image-generator-flux-free-api.p.rapidapi.com/aaaaaaaaaaaaaaaaaiimagegenerator/quick.php",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "prompt",
"value": "={{ $json.output.img_prompt }}"
},
{
"name": "style_id",
"value": "4"
},
{
"name": "size",
"value": "1-1"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "x-rapidapi-host",
"value": "ai-text-to-image-generator-flux-free-api.p.rapidapi.com"
},
{
"name": "x-rapidapi-key",
"value": "YOUR_RAPID_API_KEY"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "14334c13-43d4-457f-904e-127f3b0fff08",
"name": "下载图片",
"type": "n8n-nodes-base.httpRequest",
"position": [
288,
-48
],
"parameters": {
"url": "={{ $json.thumb }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "4b98d03e-15fa-4cf9-8fba-d614059bb22c",
"name": "OpenAI 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-416,
720
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-nano",
"cachedResultName": "gpt-5-nano"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "RZp4ut0OPqv29RiA",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "92b864a4-898d-4780-bc89-b89438b6b7bb",
"name": "tavily",
"type": "@tavily/n8n-nodes-tavily.tavilyTool",
"position": [
-128,
640
],
"parameters": {
"query": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Query', ``, 'string') }}",
"options": {
"days": 3,
"topic": "general",
"max_results": 5,
"search_depth": "advanced"
}
},
"credentials": {
"tavilyApi": {
"id": "qLj9ixhXupU9fEMj",
"name": "Tavily account"
}
},
"typeVersion": 1
},
{
"id": "db0412c2-37c4-4256-9a42-580f089284b1",
"name": "专家算法",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-576,
112
],
"parameters": {
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "=Tu es un expert en algorythme LinkedIn. Tu es capable d'analyser les meilleurs posts viraux, et comprendre pourquoi ils ont été viraux. \n\nTa mission est d'analyser tout les posts LinkedIn qui ont le plus d'impressions et de réactions en rapport avec la demande de l'utilisateur, et d'envoyer en output un framework pertinent pour créer un post viral destiné à être publier et un prompt pour générer une image pour le post !\n\nRègles :\n- Utilise ton outil de recherche \"tavily\" pour surveiller les posts LinkedIn viraux. \n- Ta réponse doit être bien structuré avec un framework exploitable.\n\nFormat de réponse : \n{\n \"framework\": \"Framework exploitable pour rédiger le post LinkedIn\",\n \"img_prompt\": \"Prompt exploitable pour générer l'image pous le post\"\n}"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "04e2ae49-6ee9-469f-8318-484a1b605460",
"name": "结构化输出解析器",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-432,
208
],
"parameters": {
"jsonSchemaExample": "{\n \"framework\": \"string\",\n \"img_prompt\": \"string\"\n}"
},
"typeVersion": 1.3
},
{
"id": "63c2485f-0186-4126-a83e-27046efbb96d",
"name": "结构化输出解析器1",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-48,
336
],
"parameters": {
"jsonSchemaExample": "{\n \"post_1\": \"string\",\n \"post_2\": \"string\",\n \"post_3\": \"string\"\n}"
},
"typeVersion": 1.3
},
{
"id": "34fb849d-522e-40aa-bda4-3bd72c70d60c",
"name": "社区经理",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
160,
240
],
"parameters": {
"text": "=Voici les 3 proposition de post : \n1 : \n{{ $json.output.post_1 }}\n2 : \n{{ $json.output.post_2 }}\n3 : \n{{ $json.output.post_3 }}",
"options": {
"systemMessage": "=Tu es un Community Manager sénior, ta mission est d'analyser les 3 propositions de posts LinkedIn que tu reçois en input, et de choisir celui qui te semble le plus viral et le transmet dans ton output. \n\nRègles :\n- Utilise ton outil tavily pour effectuer les recherches nécessaires pour savoir quelle proposition de post serai la plus virale.\n- Format de réponse : \n{\n \"post\": \"Post LinkedIn choisi\"\n}"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "a21e029e-b5b1-468b-937a-5952c0d405f3",
"name": "初级社区经理",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-192,
240
],
"parameters": {
"text": "=Voici le framework à utiliser :\n{{ $json.output.framework }}",
"batching": {},
"messages": {
"messageValues": [
{
"message": "=Tu es expert en rédaction de post LinkedIn viral, tu es community manager sénior et les algorithmes des réseaux sociaux n'ont plus aucun secret pour toi \n\nTa mission est de me proposer 3 posts LinkedIn viral grâce au framework que tu reçois en input. \n\nRègles : \n- Les posts LinkedIn doivent faire entre 500 et 900 caractères\n- Ton style de rédaction doit impérativement refléter le mien : ton amical et instructif. \n- Utilise impérativement le framework pour rédiger tes propositions de posts LinkedIn. \n\nFormat de réponse : \n\n{\n \"post_1\": \"Première proposition de post\",\n \"post_2\": \"Deuxième proposition de post\",\n \"post_3\": \"Troisième proposition de post\"\n}"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "97507dd8-0812-4109-a669-11e59d88c438",
"name": "结构化输出解析器2",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
304,
336
],
"parameters": {
"jsonSchemaExample": "{\n\t\"post\": \"string\"\n}"
},
"typeVersion": 1.3
},
{
"id": "23a40733-0b6c-4289-b44d-25431f6a0923",
"name": "发送照片消息",
"type": "n8n-nodes-base.telegram",
"position": [
496,
-48
],
"webhookId": "5c18ebd7-0e5d-4367-ba1f-6352371122b4",
"parameters": {
"chatId": "=YOUR_TELEGRAM_CHAT_ID",
"operation": "sendPhoto",
"binaryData": true,
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "AarnxB8wJEK5UvZA",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "e8740c71-f52e-428f-b327-a15aa9730db9",
"name": "发送文本消息",
"type": "n8n-nodes-base.telegram",
"position": [
496,
240
],
"webhookId": "6eb32d3f-093b-4070-8695-45c97f7a8edd",
"parameters": {
"text": "={{ $json.output.post }}",
"chatId": "=YOUR_TELEGRAM_CHAT_ID",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "AarnxB8wJEK5UvZA",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "da682c59-f46b-408c-afd5-430a91a41feb",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1360,
-288
],
"parameters": {
"width": 2240,
"height": 1200,
"content": "## LinkedIn 爆款内容生成器及图片发布器 (Telegram 机器人)"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"tavily": {
"ai_tool": [
[
{
"node": "expert_algo",
"type": "ai_tool",
"index": 0
},
{
"node": "Community Manager",
"type": "ai_tool",
"index": 0
}
]
]
},
"CM Junior": {
"main": [
[
{
"node": "Community Manager",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "download_img",
"type": "main",
"index": 0
}
]
]
},
"expert_algo": {
"main": [
[
{
"node": "CM Junior",
"type": "main",
"index": 0
},
{
"node": "generate_img",
"type": "main",
"index": 0
}
]
]
},
"download_img": {
"main": [
[
{
"node": "Send a photo message",
"type": "main",
"index": 0
}
]
]
},
"generate_img": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "expert_algo",
"type": "main",
"index": 0
}
]
]
},
"Community Manager": {
"main": [
[
{
"node": "Send a text message",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "expert_algo",
"type": "ai_languageModel",
"index": 0
},
{
"node": "CM Junior",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Community Manager",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "expert_algo",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Structured Output Parser1": {
"ai_outputParser": [
[
{
"node": "CM Junior",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Structured Output Parser2": {
"ai_outputParser": [
[
{
"node": "Community Manager",
"type": "ai_outputParser",
"index": 0
}
]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
中级 - 内容创作, 多模态 AI
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
💥 使用NanoBanana、Seedream 4、ChatGPT Image和Veo 3自动化视频广告 - VIDE
使用AI（NanoBanana、Seedream、GPT-4o、Veo 3）自动化和发布视频广告活动
Set
Code
Wait
+16
63 节点Dr. Firas
内容创作
1. 播放列表详情设置机器人副本
使用 Suno、GPT-4、Runway 和 Creatomate 创建 AI 生成的 YouTube 音乐播放列表
If
Set
Code
+22
203 节点Joseph
内容创作
UGC 广告创作器 ✅
使用 Telegram 和 GPT-4 创建 AI 生成的 UGC 营销视频
If
Set
Wait
+11
33 节点Deniz
内容创作
使用 GPT-4o、ElevenLabs 和 WaveSpeed 口型同步创建真实 UGC 视频广告
使用 GPT-4o、ElevenLabs 和 WaveSpeed 口型同步创建真实 UGC 视频广告
If
Set
Wait
+12
38 节点Muhammad Farooq Iqbal
内容创作
从产品图片生成 UGC 视频（GPT-4、Fal.ai 和 KIE.ai 通过 Telegram）
通过 Telegram 使用 GPT-4、Fal.ai 和 KIE.ai 从产品图片生成 UGC 视频
Set
Wait
Split Out
+10
28 节点Muhammad Farooq Iqbal
内容创作
内容生成器 v3
AI驱动博客自动化：使用GPT-4生成并发布SEO文章至WordPress和Twitter
If
Set
Code
+25
144 节点Jay Emp0
内容创作
